Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding

Yuu Jinnai, Kaito Ariu

Abstract
Minimum Bayes-Risk (MBR) decoding is shown to be a powerful alternative to beam search decoding for a wide range of text generation tasks. However, MBR requires a huge amount of time for inference to compute the MBR objective, which makes the method infeasible in many situations where response time is critical. Confidence-based pruning (CBP) (Cheng and Vlachos, 2023) has recently been proposed to reduce the inference time in machine translation tasks. Although it is shown to significantly reduce the amount of computation, it requires hyperparameter tuning using a development set to be effective. To this end, we propose Adaptive Minimum Bayes-Risk (AMBR) decoding, a hyperparameter-free method to run MBR decoding efficiently. AMBR is derived from the observation that the problem of computing the sample-based MBR objective is the medoid identification problem. AMBR uses the Correlated Sequential Halving (CSH) algorithm (Baharav and Tse, 2019), the algorithm with the best performance guarantee to date for the medoid identification problem, to compute the sample-based MBR objective. We evaluate AMBR on machine translation, text summarization, and image captioning tasks. The results show that AMBR achieves on par with CBP, with CBP selecting hyperparameters through an Oracle for each given computation budget.
Anthology ID:
2024.findings-acl.505
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8547–8566
Language:
URL:
https://aclanthology.org/2024.findings-acl.505
DOI:
Bibkey:
Cite (ACL):
Yuu Jinnai and Kaito Ariu. 2024. Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding. In Findings of the Association for Computational Linguistics ACL 2024, pages 8547–8566, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding (Jinnai & Ariu, Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.505.pdf
PDF Search